mirrors/icefall
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
497 Commits 5 Branches 3 Tags
Commit Graph

400 Commits

Author SHA1 Message Date
pkufool
6a937ffa40 Minor fixes for streaming decoding 2022-06-18 08:41:52 +08:00
pkufool
88ed814197 Fix jit export for torch 1.6 2022-06-18 08:35:25 +08:00
pkufool
413ca2ef77 Merge remote-tracking branch 'origin/master' into streaming-conformer 2022-06-13 19:10:44 +08:00
pkufool
85ddfd958c Minor fixes 2022-06-10 19:06:06 +08:00
Fangjun Kuang
9f6c748b30
Add links to sherpa. (#417) 
* Add links to sherpa.
 2022-06-10 12:19:18 +08:00
Fangjun Kuang
dbda1644b5
Replace load_manifest_lazy with load_manifest for MUSAN. (#412) 2022-06-09 11:42:18 +08:00
Fangjun Kuang
ed66877694
Replace ChunkedLilcomHdf5Writer with LilcomChunkyWriter. (#411) 2022-06-09 11:18:52 +08:00
Quandwang
8512aaf585
fix typos (#409) 2022-06-08 20:08:44 +08:00
Fangjun Kuang
1094a3cb37
Replace LilcomChunkyWriter with ChunkedLilcomHdf5Writer. (#404) 2022-06-07 18:14:25 +08:00
pkufool
aebe9c22dd Minor fixes 2022-06-07 15:59:58 +08:00
pkufool
d7be9bd9c5 Minor fixes 2022-06-07 12:00:26 +08:00
Fangjun Kuang
80c46f0abd
Fix exporting emformer with torchscript using torch 1.6.0 (#402) 2022-06-07 09:19:37 +08:00
pkufool
1c794e32b0 Minor fixes 2022-06-06 20:19:49 +08:00
pkufool
09b0c54983 Minor fixes 2022-06-06 17:56:22 +08:00
Fangjun Kuang
29fa878fff
Fix Emformer for torchscript using torch 1.6.0 (#401) 2022-06-06 17:08:07 +08:00
Fangjun Kuang
f1abce72f8
Use jsonl for CutSet in the LibriSpeech recipe. (#397) 
* Use jsonl for cutsets in the librispeech recipe.

* Use lazy cutset for all recipes.

* More fixes to use lazy CutSet.

* Remove force=True from logging to support Python < 3.8

* Minor fixes.

* Fix style issues.
 2022-06-06 10:19:16 +08:00
pkufool
3aacf75652 fix relative positional encoding in streaming decoding for compution saving 2022-06-06 06:46:40 +08:00
Zengwei Yao
148f69d8d9
Update RESULTS.md (#388) 
* update RESULT.md about pruned_transducer_stateless4

* Update RESULT.md

This PR is only to update RESULT.md about pruned_transducer_stateless4.

* set default value of --use-averaged-model to True

* update RESULTS.md and add decode command

* minor fix

* update export.py

* add uploaded files links

* update link

* fix typos
 2022-06-04 15:52:35 +08:00
pkufool
fc54a99a56 Cutting off invalid frames of encoder_embed output 2022-06-02 14:19:08 +08:00
pkufool
9629be124d mask the initial cache 2022-06-01 21:50:02 +08:00
Fangjun Kuang
fbfc98f1d3
Add streaming Emformer stateless RNN-T. (#390) 
* Add streaming Emformer stateless RNN-T.

* Update results for streaming Emformer.

* Minor fixes.
 2022-06-01 14:31:47 +08:00
pkufool
0325e3a04e Add torch.jit.export 2022-05-29 16:25:01 +08:00
pkufool
605838da55 Fix style 2022-05-29 07:48:52 +08:00
pkufool
aecaecfb17 Fix style 2022-05-29 07:35:52 +08:00
pkufool
fb3f3d2526 Fix style 2022-05-29 07:33:54 +08:00
pkufool
b23db42486 Fix conv cache error, support async streaming decoding 2022-05-29 07:06:44 +08:00
LIyong.Guo
c4ee2bc0af
[Ready to merge]stateless6: states4 + hubert distillation. (#387) 
* a copy of stateless4 as base

* distillation with hubert

* fix typo

* example usage

* usage

* Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py

Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>

* fix comment

* add results of 100hours

* Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py

Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>

* Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py

Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>

* check fairseq and quantization

* a short intro to distillation framework

* Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py

Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>

* add intro of statless6 in README

* fix type error of dst_manifest_dir

* Update egs/librispeech/ASR/pruned_transducer_stateless6/hubert_xlarge.py

Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>

* make export.py call stateless6/train.py instead of stateless2/train.py

* update results by stateless6

* adjust results format

* fix typo

Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
 2022-05-28 12:37:50 +08:00
pkufool
364bccb2e3 Merge branch 'master' into streaming-conformer 2022-05-26 10:29:08 +08:00
pkufool
4f2ef237eb streaming for pruned_transducer_stateless4 2022-05-26 10:22:05 +08:00
pkufool
e923b1b336 Minor fixes 2022-05-26 10:00:18 +08:00
Ewald Enzinger
8c5722de8c
[egs] Add prefix when reading manifests due to recent lhotse changes (#382) 
* [egs] Add prefix when reading manifests due to recent lhotse changes

* Fix wenetspeech

* Fix style issues
 2022-05-23 23:37:35 +08:00
Fangjun Kuang
2f1e23cde1
Narrower and deeper conformer (#330) 
* Copy files for editing.

* Add random combine from #229.

* Minor fixes.

* Pass model parameters from the command line.

* Fix warnings.

* Fix warnings.

* Update readme.

* Rename to avoid conflicts.

* Update results.

* Add CI for pruned_transducer_stateless5

* Typo fixes.

* Remove random combiner.

* Update decode.py and train.py to use periodically averaged models.

* Minor fixes.

* Revert to use random combiner.

* Update results.

* Minor fixes.
 2022-05-23 14:39:11 +08:00
pkufool
7cc697c03a support streaming on pruned_transducer_stateless2; add delay penalty; fixes for decode states 2022-05-22 17:14:17 +08:00
pkufool
118b09463d Add more documents 2022-05-20 15:26:45 +08:00
Daniel Povey
4e23fb2252
Improve diagnostics code memory-wise and accumulate more stats. (#373) 
* Update diagnostics, hopefully print more stats.

# Conflicts:
#	egs/librispeech/ASR/pruned_transducer_stateless4b/train.py

* Remove memory-limit options arg

* Remove unnecessary option for diagnostics code, collect on more batches
 2022-05-19 11:45:59 +08:00
pkufool
5bd2490b44 support streaming in conformer 2022-05-18 23:26:24 +08:00
Fangjun Kuang
f6ce135608
Various fixes to support torch script. (#371) 
* Various fixes to support torch script.

* Add tests to ensure that the model is torch scriptable.

* Update tests.
 2022-05-16 21:46:59 +08:00
Fangjun Kuang
f23dd43719
Update results for libri+giga multi dataset setup. (#363) 
* Update results for libri+giga multi dataset setup.
 2022-05-14 21:45:39 +08:00
Fangjun Kuang
0f180b3ce2
Validate that there are no OOV tokens in BPE-based lexicons. (#359) 
* Validate that there are no OOV tokens in BPE-based lexicons.

* Typo fixes.
 2022-05-13 14:00:35 +08:00
Fangjun Kuang
7b7acdf369
Support --iter in export.py (#360) 2022-05-13 10:51:44 +08:00
Fangjun Kuang
aeb8986e35
Ignore padding frames during RNN-T decoding. (#358) 
* Ignore padding frames during RNN-T decoding.

* Fix outdated decoding code.

* Minor fixes.
 2022-05-13 07:39:14 +08:00
Fangjun Kuang
bc284e88e6
Run decode.py in GitHub actions. (#356) 2022-05-10 14:51:34 +08:00
Zengwei Yao
20f092e709
Support decoding with averaged model when using --iter (#353) 
* support decoding with averaged model when using --iter

* minor fix

* monir fix of copyright date
 2022-05-07 13:09:11 +08:00
Zengwei Yao
c059ef3169
Keep model_avg on cpu (#348) 
* keep model_avg on cpu

* explicitly convert model_avg to cpu

* minor fix

* remove device convertion for model_avg

* modify usage of the model device in train.py

* change model.device to next(model.parameters()).device for decoding

* assert params.start_epoch>0

* assert params.start_epoch>0, params.start_epoch
 2022-05-07 10:42:34 +08:00
Fangjun Kuang
32f05c00e3
Save batch to disk on exception. (#350) 2022-05-06 17:49:40 +08:00
Zengwei Yao
00c48ec1f3
Model average (#344) 
* First upload of model average codes.

* minor fix

* update decode file

* update .flake8

* rename pruned_transducer_stateless3 to pruned_transducer_stateless4

* change epoch number counter starting from 1 instead of 0

* minor fix of pruned_transducer_stateless4/train.py

* refactor the checkpoint.py

* minor fix, update docs, and modify the epoch number to count from 1 in the pruned_transducer_stateless4/decode.py

* update author info

* add docs of the scaling in function average_checkpoints_with_averaged_model
 2022-05-05 21:20:04 +08:00
Fangjun Kuang
8635fb4334
Fix decoding for gigaspeech in the libri + giga setup. (#345) 2022-05-05 20:58:46 +08:00
Fangjun Kuang
e1c3e98980
Save batch to disk on OOM. (#343) 
* Save batch to disk on OOM.

* minor fixes

* Fixes after review.

* Fix style issues.
 2022-05-05 15:09:23 +08:00
Fangjun Kuang
6af15914fa
Validate generated manifest files. (#338) 2022-05-03 07:02:54 +08:00
Fangjun Kuang
6dc2e04462
Update results. (#340) 
* Update results.

* Typo fixes.
 2022-04-29 15:49:45 +08:00